Stars
[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations
SpatialLM: Training Large Language Models for Structured Indoor Modeling
Official code for the CVPR 2025 paper "Navigation World Models".
[CVPR 2024] "LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning"; an interactive Large Language 3D Assistant.
[ECCV 2024 Best Paper Candidate] PointLLM: Empowering Large Language Models to Understand Point Clouds
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
[ECCV 2024] Official implementation of "RangeLDM: Fast Realistic LiDAR Point Cloud Generation"
Graduate-Level Courses (Electrical Engineering & Computer Science) at NTU, Singapore
[ICCV 2025] Official implementation of the paper “MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”
Official PyTorch implementation of SegFormer
An open source implementation of CLIP.
[NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
Official implementation of "LidarDM: Generative LiDAR Simulation in a Generated World" (ICRA 2025)
[ICLR 2025 Spotlight] Official implementation for "DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes"
LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models (ICRA 2024)
[CVPR 2024] Official implementation of "Towards Realistic Scene Generation with LiDAR Diffusion Models"
Simulator-conditioned Driving Scene Generation
(CVPR 2023) The official project of "3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds"
[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI
A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.
Pointcept: a codebase for point cloud perception research. Latest works: Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral), PPT (CVPR'24), MSC (CVPR'23)
[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)
The official implementation for "Spherical Transformer for LiDAR-based 3D Recognition" (CVPR 2023).